[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAM9d7cjHndHrcH95uwmYRMRpm-a0kX2BHQ1jzmyo6f48w69jbg@mail.gmail.com>
Date: Mon, 26 Jun 2023 16:14:45 -0700
From: Namhyung Kim <namhyung@...nel.org>
To: Conor Dooley <conor@...nel.org>
Cc: Inochi Amaoto <inochiama@...look.com>,
Peter Zijlstra <peterz@...radead.org>,
Ingo Molnar <mingo@...hat.com>,
Arnaldo Carvalho de Melo <acme@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Jiri Olsa <jolsa@...nel.org>, Ian Rogers <irogers@...gle.com>,
Adrian Hunter <adrian.hunter@...el.com>,
Paul Walmsley <paul.walmsley@...ive.com>,
Palmer Dabbelt <palmer@...belt.com>,
Albert Ou <aou@...s.berkeley.edu>,
Nikita Shubin <n.shubin@...ro.com>,
linux-kernel@...r.kernel.org, linux-perf-users@...r.kernel.org,
linux-riscv@...ts.infradead.org
Subject: Re: [PATCH V3] perf vendor events riscv: add T-HEAD C9xx JSON file
Hello,
On Sat, Jun 24, 2023 at 1:54 AM Conor Dooley <conor@...nel.org> wrote:
>
> On Fri, Jun 23, 2023 at 09:35:01PM -0700, Namhyung Kim wrote:
> > On Fri, Jun 23, 2023 at 6:33 PM Inochi Amaoto <inochiama@...look.com> wrote:
>
> > >
> > > As for c9xx wildcard, the T-HEAD provides a `MCPUID` vendor CSR to allow
> > > its CKLINK to get the detail CPU info. The format of this CSR are:
> > >
> > > ------------------------------------------------
> > > |31 28|27 26|25 22|21 18|17 8|7 0|
> > > | index | WLRL | family | class | model | WLRL |
> > > ------------------------------------------------
> > >
> > > And for C9xx series (only index 0000 is vaild for us, as `MCPUID` also
> > > provides other index).
> > >
> > > | 0000 | xx | 0100 | class | xxxxxxxxxx | xxxxxxxx |
> > >
> > > The class codes are:
> > >
> > > C910: 0011
> > > c906: 0100
> > >
> > > The CSR is a M-mode only CSR, so now I'm exploring a clean way to
> > > integrate this CSR into the kernel. Any advice?
>
> See for example how riscv_cpuinfo_starting() reads mvendorid & Co.
>
> > I don't know about the details. Is this CSR available from user space?
> > If not, you could add it somewhere in the sysfs.
>
> Machine mode is the highest privilege level, Supervisor mode is next &
> User mode is the lowest. Typically the kernel runs in Supervisor mode.
Maybe you're interested in this thread for user visible identifiers.
https://lore.kernel.org/all/1687245156-61215-1-git-send-email-renyu.zj@linux.alibaba.com/
Thanks,
Namhyung
Powered by blists - more mailing lists